Skip to content
UtilityHub Logo
UtilityHub
Search

AI News & Insights

Older items first published newest-to-oldest across the feed — page 120 of 123.

How AI training scales
Business

How AI training scales

We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural network training on a wide range of tasks. Since complex tasks tend to have...

OpenAI Blog · 95mo ago
4 min
Quantifying generalization in reinforcement learning
Business

Quantifying generalization in reinforcement learning

We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experience to novel situations and has already helped clarify a longstanding puzzle...

#agent
OpenAI Blog · 96mo ago
4 min
Spinning Up in Deep RL
Business

Spinning Up in Deep RL

We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning. Spinning Up consists of crystal-clear...

OpenAI Blog · 97mo ago
4 min
Learning concepts with energy functions
Business

Learning concepts with energy functions

We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. ...

OpenAI Blog · 97mo ago
4 min
Reinforcement learning with prediction-based rewards
Business

Reinforcement learning with prediction-based rewards

We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time...

#agent
OpenAI Blog · 97mo ago
4 min
Learning complex goals with iterated amplification
Business

Learning complex goals with iterated amplification

We’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into...

OpenAI Blog · 97mo ago
4 min
OpenAI Scholars 2019: Applications open
Business

OpenAI Scholars 2019: Applications open

We are now accepting applications for our second cohort of OpenAI Scholars, a program where we provide 6–10 stipends and mentorship to individuals from underrepresented groups to study deep...

#openai
OpenAI Blog · 97mo ago
4 min
The International 2018: Results
Business

The International 2018: Results

OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week, maintaining a good chance of winning for the first 20–35 minutes of both games.

#openai
OpenAI Blog · 99mo ago
4 min
OpenAI Five Benchmark: Results
Business

OpenAI Five Benchmark: Results

Yesterday, OpenAI Five won a best-of-three against a team of 99. 95th percentile Dota players: Blitz, Cap, Fogged, Merlini, and MoonMeander—four of whom have played Dota professionally—in front of...

#openai
OpenAI Blog · 100mo ago
4 min
Learning dexterity
Business

Learning dexterity

We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.

OpenAI Blog · 100mo ago
4 min
OpenAI Five Benchmark
Business

OpenAI Five Benchmark

The OpenAI Five Benchmark match is now over!

#openai
OpenAI Blog · 100mo ago
4 min
Glow: Better reversible generative models
Business

Glow: Better reversible generative models

We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture.

OpenAI Blog · 101mo ago
4 min
Learning Montezuma’s Revenge from a single demonstration
Business

Learning Montezuma’s Revenge from a single demonstration

We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent...

#agent
OpenAI Blog · 101mo ago
4 min
OpenAI Five
Business

OpenAI Five

Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.

#openai
OpenAI Blog · 101mo ago
4 min
Retro Contest: Results
Business

Retro Contest: Results

The first run of our Retro Contest—exploring the development of algorithms that can generalize from previous experience—is now complete.

OpenAI Blog · 101mo ago
4 min
OpenAI Fellows Fall 2018
Business

OpenAI Fellows Fall 2018

We’re now accepting applications for the next cohort of OpenAI Fellows, a program which offers a compensated 6-month apprenticeship in AI research at OpenAI.

#openai
OpenAI Blog · 102mo ago
4 min
Gym Retro
Business

Gym Retro

We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games...

OpenAI Blog · 102mo ago
4 min
AI and compute
Business

AI and compute

We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3. 4-month doubling time (by comparison,...

OpenAI Blog · 102mo ago
4 min
AI safety via debate
Business

AI safety via debate

We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.

#agent
OpenAI Blog · 103mo ago
4 min
Evolved Policy Gradients
Business

Evolved Policy Gradients

We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, which can enable fast training on novel tasks. ...

#agent
OpenAI Blog · 103mo ago
4 min